Welcome to the Neural Networks Hands-On Projects repository! 🧠💻
This repository serves as a comprehensive collection of hands-on projects designed to complement theoretical learning about neural networks. Each project offers a practical, step-by-step implementation of different neural network concepts using popular frameworks like TensorFlow, Keras, PyTorch, and more.
PyTorch implementation of 'Deep-Emotion,' a facial expression recognition using attentional convolutional network. This repository provides an end-to-end deep learning solution for facial expression analysis.
Each project includes detailed documentation, code samples, and explanations to help you grasp concepts effectively. Feel free to explore, experiment, and expand upon these projects as you dive deeper into the world of neural networks!
Happy learning and coding! 🚀🧠
The overarching goal of the project is to understand and quantify how neural activity relates to changes in behavior, specifically changes in pupil coordinates. The project aims to achieve this through data preprocessing, visualization, dimensionality reduction, machine learning modeling, and time series analysis, with a focus on layer-specific insights. The performance metrics of the machine learning models will provide insights into the strength of the relationship between neural responses and behavioral changes.
In this implementation project, the aim is to replicate the self-supervised architecture proposed in the paper "Improving Fairness of Automated Chest X-ray Diagnosis by Contrastive Learning." Key components include designing a custom loss function, adapting data loading to handle three images at once, utilizing ResNet or EfficientNet as the model backbone, incorporating a contrastive learning head, and evaluating the model's performance in downstream medical image classification tasks. This project not only offers hands-on experience with cutting-edge self-supervised learning but also contributes to the advancement of fairness in automated medical diagnosis, aligning with emerging trends in machine learning research.